https://www.cnblogs.com/P3nguin/p/7777239.html
卷积
削峰平谷,平滑的作用,可用高斯,平均等矩阵
https://blog.csdn.net/qq_39521554/article/details/79083864
https://en.wikipedia.org/wiki/Convolution
卷积应用:cv.pyrDown https://blog.csdn.net/jxlijunhao/article/details/17611411 或https://blog.csdn.net/davebobo/article/details/51885043
https://baike.baidu.com/item/%E6%9B%B2%E7%BA%BF%E6%8B%9F%E5%90%88/5893992?fr=aladdin
曲线拟合
https://blog.csdn.net/mosthandsomep/article/details/79776260
多项式拟合
最小二乘法多项式曲线拟合原理与实现
https://blog.csdn.net/StupidAutofan/article/details/78924601
https://blog.csdn.net/xwl198937/article/details/52210156
https://blog.csdn.net/JairusChan/article/details/7517773
https://blog.csdn.net/guduruyu/article/details/72866144
【算法+OpenCV】基于opencv的直线和曲线拟合与绘制(最小二乘法)
https://blog.csdn.net/xxworld22/article/details/85010135
利用奇异值分解(SVD)求解线性最小二乘问题
https://blog.csdn.net/zhongkejingwang/article/details/43053513
奇异值分解(SVD)原理详解及推导
https://blog.csdn.net/u014652390/article/details/52789591
opencv CvSolve函数深度解析
https://blog.csdn.net/qq_23869697/article/details/80610361
期望值、方差、协方差和协方差矩阵
https://blog.csdn.net/GoodShot/article/details/79940438
协方差的意义--两个变量的相关性(正相关、负相关、不相关)
numpy中轴的概念
track = np.cumsum(np.random.rand(500000, 2)-0.5, axis=0)
>>> a= np.array([[[1,2,3],[4,5,6]],[[7,8,9],[10,11,12]]])
>>> a
array([[[ 1, 2, 3],
[ 4, 5, 6]],
[[ 7, 8, 9],
[10, 11, 12]]])
>>> b= np.cumsum(a,0)
>>> b
array([[[ 1, 2, 3],
[ 4, 5, 6]],
[[ 8, 10, 12],
[14, 16, 18]]], dtype=int32)
>>> b= np.cumsum(a,1)
>>> b
array([[[ 1, 2, 3],
[ 5, 7, 9]],
[[ 7, 8, 9],
[17, 19, 21]]], dtype=int32)
>>> b= np.cumsum(a,2)
>>> b
array([[[ 1, 3, 6],
[ 4, 9, 15]],
[[ 7, 15, 24],
[10, 21, 33]]], dtype=int32)
https://www.cnblogs.com/zl1991/p/4913450.html
RGB/BGR HSV HSL